Image denoising assessment using anisotropic stack filtering

TL;DR

This paper introduces a novel anisotropy-based measure derived from stack filtering to effectively estimate noise levels in images, aiding in the assessment of denoising quality.

Contribution

It proposes a new anisotropy measure using directional entropy and stack filtering, providing a robust noise indicator for image quality assessment.

Findings

The measure correlates well with noise levels in artificial and real images.

It effectively distinguishes between different denoising algorithm performances.

Empirical results validate its usefulness as a noise indicator.

Abstract

In this paper we propose a measure of anisotropy as a quality parameter to estimate the amount of noise in noisy images. The anisotropy of an image can be determined through a directional measure, using an appropriate statistical distribution of the information contained in the image. This new measure is achieved through a stack filtering paradigm. First, we define a local directional entropy, based on the distribution of 0's and 1's in the neigborhood of every pixel location of each stack level. Then the entropy variation of this directional entropy is used to define an anisotropic measure. The empirical results have shown that this measure can be regarded as an excellent image noise indicator, which is particularly relevant for quality assessment of denoising algorithms. The method has been evaluated with artificial and real-world degraded images.